Voice synthesis GPU peak allocated — C013

Voice candidates were scored blind by embedding similarity and intelligibility, then chosen by listening — samples are not published.

Single reading

1,990 MiB

MEASURED recorded 13 September 2026

Protocol

Test definition

Offline ECAPA-TDNN speaker-embedding cosine to a fixed TEST-only reference centroid and Whisper round-trip WER over eight fixed original sentences unless stated. Cold model load 10.77 s.

Limits

Limitations

  • MEASURED_UNQUALIFIED. Similarity is diagnostic, not identity or quality; scores are only comparable within one reference population. Owner preference did not track similarity. DO NOT publish audio (rights flag in voice.md).

Log

Recorded values

Date Value Evidence Samples Source
13 September 2026 1,990 MiB MEASURED 8

Source paths refer to the private JARVIS repository and runtime records. They are listed for audit and are not published.